Skip to content

BugTraceAI/BugTraceAI

Repository files navigation

BugTraceAI

BugTraceAI

Autonomous AI-powered security scanning platform

Website Wiki DeepWiki Live Demo Demo Report License Version

Python React FastAPI Go Playwright Docker


Disclaimer

This platform is provided for educational and authorized security testing purposes only.

  • Only test applications for which you have explicit, written authorization
  • AI output may contain inaccuracies, false positives, or false negatives
  • It is not a substitute for professional security auditing
  • The creators assume no liability for misuse or damage

Always verify findings manually.


What is BugTraceAI?

BugTraceAI is an opensource, self-hosted framework for bug bounty hunting and penetration testing. It combines autonomous AI agents with real security tools to discover, analyze, exploit, and validate vulnerabilities independently.

This is NOT a wrapper around existing tools. It is an autonomous multi-agent system where AI agents make intelligent decisions about what to test, how to mutate payloads, and when findings are real.

Core Principles

Principle Description
Privacy-First Everything runs locally. No telemetry, no tracking, no cloud dependency
Opensource AGPL-3.0 licensed. All code, prompts, and algorithms are public
Self-Hosted Your data stays on your infrastructure
Modular Use components independently or together
Docker-Native One-command deployment via Launcher

The Ecosystem

BugTraceAI is composed of 3 independent but interconnected components:

Component Description Tech Stack Repository
BugTraceAI-CLI Autonomous AI security scanner. Multi-agent pipeline with Go fuzzers, Playwright browser validation, and AI-driven analysis Python + FastAPI + Go + Playwright BugTraceAI-CLI
BugTraceAI-WEB Web dashboard with 20+ AI security tools, real-time scan monitoring, and CLI control center React + Express + PostgreSQL BugTraceAI-WEB
BugTraceAI-Launcher One-command Docker deployment wizard with interactive setup and service management Bash + Docker Compose BugTraceAI-Launcher
MCP Ecosystem Extensible agent framework using the Model Context Protocol. Includes integrated Kali Linux and ReconFTW agents MCP + Docker + Python reconftw-mcp

Each component works independently. Use the WEB alone for AI analysis, the CLI alone for autonomous scanning, or deploy everything together with the Launcher.


Architecture

                    +----------------------------+
                    |      BugTraceAI-WEB        |
                    |   React + Express + PgSQL  |
                    |   Port 6869 / Port 3001    |
                    +-------------+--------------+
                                  |
                          REST API + WebSocket
                                  |
                    +-------------+-----------------+
                    |      BugTraceAI-CLI           |
                    |   FastAPI + SQLite + LanceDB  |
                    |        Port 8000              |
                    +---+--------+-------------+----+
                        |        |             |
                   +----+--+ +---+------+ +----+------+
                   |Go     | |Playwright| |AI Agents  |
                   |Fuzzers| |Browser   | |OpenRouter |
                   +-------+ +----------+ +-----------+

SQLite is the source of truth for all scan data. PostgreSQL is local to each WEB instance for chats, settings, and analysis. They work autonomously OR together -- multiple WEB instances can connect to one CLI over the network.

For detailed architecture documentation, see the Wiki.


Scanning Pipeline

The CLI runs a 6-phase autonomous pipeline:

Phase Name Description
1 Discovery Crawl and spider the target to map the attack surface
2 Analysis Multi-persona AI analysis with consensus voting
3 Consolidation Deduplicate findings and distribute to specialist queues
4 Exploitation 14 specialist agents (XSS, SQLi, SSRF, IDOR, LFI, RCE, XXE, JWT, Open Redirect, Prototype Pollution, CSTI, Mass Assignment, Header Injection, BAC Detection) with Go fuzzers and AI-mutated payloads
5 Validation Chrome DevTools Protocol + Vision AI screenshot analysis confirms findings
6 Reporting PoC enrichment with WET/DRY traceability, AI-generated technical and executive reports

The pipeline includes a circuit breaker that auto-pauses scanning when the target becomes unresponsive, and supports authenticated scanning with pre-configured tokens or automatic login flows.

For the full pipeline documentation, see the Wiki.


Demo Report

Want to see what BugTraceAI produces? Try the live demo or download a real scan report generated against BugStore -- our deliberately vulnerable practice app.

Live Demo   Download Demo Report

Scan highlights: 145 findings (43 validated) -- SQL Injection, XSS, LFI, CSTI, IDOR, JWT, RCE, Broken Access Control, Open Redirect, Prototype Pollution, GraphQL, SSRF, and more.

The zip includes the full markdown report, validated findings JSON, specialist agent results with WET/DRY traceability, reconnaissance data, and PoC enrichment output.


Quick Start

Requirements

  • Docker 24.0+
  • Git
  • 4 GB RAM (8 GB recommended)
  • 10 GB disk space
  • OpenRouter API key

One-Command Install

git clone https://github.com/BugTraceAI/BugTraceAI-Launcher.git ~/bugtraceai-launcher
~/bugtraceai-launcher/launcher.sh

The interactive wizard handles deployment mode selection, API key configuration, and port assignment.

Deployment Modes

Mode What You Get Use Case
Full Platform WEB + CLI auto-connected Complete scanning + dashboard
Standalone CLI Headless scanner + API CI/CD pipelines, automation
Standalone WEB Dashboard + AI tools Manual analysis without scanning

Alternative: Individual Components

# CLI only
git clone https://github.com/BugTraceAI/BugTraceAI-CLI.git
cd BugTraceAI-CLI
pip install -r requirements.txt
python -m bugtrace --help

# WEB only
git clone https://github.com/BugTraceAI/BugTraceAI-WEB.git
cd BugTraceAI-WEB
docker compose up

Documentation

Full documentation is available in the Project Wiki:


Community & Support

Resource Link
Website bugtraceai.com
Wiki GitHub Wiki
DeepWiki AI-powered docs
Issues GitHub Issues
Twitter @yz9yt

Contributing

We welcome contributions: bug reports, feature requests, PRs, documentation improvements, and community tools. Open an issue on the respective repository to get started.


License

AGPL-3.0 License — Free to use, modify, and distribute. If you modify and distribute or offer as a service, you must share your changes under the same license.

See LICENSE file in each repository.


BugTraceAI -- Build your own self-hosted pentesting platform.
Albert C (@yz9yt)

About

Autonomous AI-powered security scanning platform — CLI scanner, web dashboard, and one-command Docker deployment

Resources

License

Contributing

Stars

Watchers

Forks

Packages

 
 
 

Contributors